sched: avoid large irq-latencies in smp-balancing

SMP balancing is done with IRQs disabled and can iterate the full rq.
When rqs are large this can cause large irq-latencies. Limit the nr of
iterations on each run.

This fixes a scheduling latency regression reported by the -rt folks.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Tested-by: Gregory Haskins <ghaskins@novell.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

include/linux/sched.h

@@ -1466,6 +1466,7 @@ extern unsigned int sysctl_sched_batch_wakeup_granularity;
 extern unsigned int sysctl_sched_child_runs_first;
 extern unsigned int sysctl_sched_features;
 extern unsigned int sysctl_sched_migration_cost;
+extern unsigned int sysctl_sched_nr_migrate;
 
 int sched_nr_latency_handler(struct ctl_table *table, int write,
 		struct file *file, void __user *buffer, size_t *length,

kernel/sched.c

@@ -471,6 +471,12 @@ const_debug unsigned int sysctl_sched_features =
 
 #define sched_feat(x) (sysctl_sched_features & SCHED_FEAT_##x)
 
+/*
+ * Number of tasks to iterate in a single balance run.
+ * Limited because this is done with IRQs disabled.
+ */
+const_debug unsigned int sysctl_sched_nr_migrate = 32;
+
 /*
  * For kernel-internal use: high-speed (but slightly incorrect) per-cpu
  * clock constructed from sched_clock():
@@ -2235,7 +2241,7 @@ balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
 	      enum cpu_idle_type idle, int *all_pinned,
 	      int *this_best_prio, struct rq_iterator *iterator)
 {
-	int pulled = 0, pinned = 0, skip_for_load;
+	int loops = 0, pulled = 0, pinned = 0, skip_for_load;
 	struct task_struct *p;
 	long rem_load_move = max_load_move;
 
@@ -2249,10 +2255,10 @@ balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
 	 */
 	p = iterator->start(iterator->arg);
 next:
-	if (!p)
+	if (!p || loops++ > sysctl_sched_nr_migrate)
 		goto out;
 	/*
-	 * To help distribute high priority tasks accross CPUs we don't
+	 * To help distribute high priority tasks across CPUs we don't
 	 * skip a task if it will be the highest priority task (i.e. smallest
 	 * prio value) on its new queue regardless of its load weight
 	 */
@@ -2269,8 +2275,7 @@ next:
 	rem_load_move -= p->se.load.weight;
 
 	/*
-	 * We only want to steal up to the prescribed number of tasks
-	 * and the prescribed amount of weighted load.
+	 * We only want to steal up to the prescribed amount of weighted load.
 	 */
 	if (rem_load_move > 0) {
 		if (p->prio < *this_best_prio)

kernel/sysctl.c

@@ -301,6 +301,14 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_nr_migrate",
+		.data		= &sysctl_sched_nr_migrate,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 644,
+		.proc_handler	= &proc_dointvec,
+	},
 #endif
 	{
 		.ctl_name	= CTL_UNNUMBERED,